AI Agent Benchmarks

Follow this topic Ask about this topic

Momentum

148 papers in the last four weeks, up 185% on the four weeks before. 1.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,013

Aug 7, 2026cs.AI

Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework

Large language model (LLM) agents increasingly operate through long-horizon trajectories involving user instructions, tool use, external observations, and memory. Existing benchmarks primarily evaluate behavioral outcomes but provide limited support for fine-grained attribution analysis. We introduce trajectory attribution and develop a benchmark and annotation framework for this task. The benchmark organizes heterogeneous trajectories under a unified component schema and provides annotations of the primary attribution component, together with attack and execution chains where applicable. Instantiating the benchmark with trajectories from AgentDojo and the Stage and Canary settings of Agent3Sigma yields more than 1,300 annotated trajectories covering task-aligned actions, unsafe actions, and safety refusals. The benchmark defines two evaluation tasks, primary attribution localization and attribution-chain recovery, and provides reference baselines based on incremental trajectory contribution and component-level leave-one-out perturbation. It captures diverse attribution settings, including local and long-range attribution as well as structured attribution chains. Reference baseline results exhibit substantial performance differences across these settings, providing an initial characterization of the benchmark's attribution challenges. Beyond this initial instantiation, we release a reusable annotation skill that enables trajectories generated by new agent models to be standardized, annotated, and evaluated under the same framework. Project resources and future releases are available at https://github.com/chenjing-2024/agent-trajectory-attribution.

Jing Chen, Yang Sun, Li Zhang +2

Huawei Technologies Ltd.

Long-Horizon Agent Evaluation AI Agent Benchmarks Agent Trajectory Analysis

Aug 7, 2026cs.AI

TRACE: A Multi-Layer Benchmark for Human AI Controller Coordination Under Drift and Failure

Modern cyber-physical and AI-assisted systems couple human operators, AI decision modules, and automated controllers in a single control loop, so trustworthiness depends on the whole loop, not any one model. Yet no standard benchmark captures time-aligned, multi-layer traces of how drift and failures propagate across these layers, so we cannot diagnose where coordination breaks down, why, or how to recover. This paper targets one facet of that gap: drift, a deviation that can originate in any stack layer and that conventional single-modality monitoring cannot localize to a layer or pin to an onset time. We construct a benchmark by injecting controlled drift into traces derived from ALFRED, a grounded-instruction benchmark for everyday household tasks, yielding 1,918 drifted traces. Each trace is a time-aligned sequence of per-step records across five execution layers (state, observation, decision, rules, control), labeled with the drift type, affected layer, onset time, responsible actor, and causal mechanism, and validated by independent raters with inter-annotator agreement reported. We pair the dataset with a leak-aware protocol that removes a near-perfect onset leak, and a baseline study across classical, recurrent, and attention-based model families. Under this honest protocol, drift is identifiable and attributable well above random and majority baselines across every family (affected layer macro-F1 near 0.70, responsible actor near 0.85, causal mechanism near 0.49), and heavy attention offers no advantage over simpler models on this symbolic benchmark.

Joshua Zuniga, Srinivasan Subramanian, Ramya Madhuri Narapureddy +1

College of Computing and Software Engineering Kennesaw State University Marietta, GA, USA

Agent Failure Analysis AI Agent Benchmarks AI Agent Monitoring Change-Point Detection Human-AI Collaboration

Aug 6, 2026cs.CL

Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents

Task-oriented conversational agents are evaluated using curated or automatically generated benchmarks, yet benchmark quality is rarely assessed. Poor benchmarks may contain inconsistent tasks, simplistic scenarios, or limited policy coverage, leading to unreliable evaluations. We introduce a reference-free framework that uses LLM judges to assess benchmark consistency, complexity, and policy coverage, while providing actionable diagnostics of weaknesses. We validate the framework by demonstrating agreement with independent human annotations and by evaluating benchmarks generated by LLMs of varying capabilities, as well as benchmarks subjected to controlled quality-degrading perturbations. Across domains and judge models, the proposed metrics consistently distinguish between benchmark quality levels. We further demonstrate the framework's applicability to manually curated benchmarks. Our framework offers a practical approach for evaluating synthetic and manually curated conversational-agent benchmarks.

Noam Koren, Roy Bar-Haim, Abigail Goldsteen

IBM Research

AI Agent Benchmarks Task-Oriented Dialogue Systems

Aug 6, 2026cs.AI

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them. This makes automated harness optimization -- the iterative and evaluation-guided improvement of a harness by an AI system -- both an important route to improving AI systems and a demanding capability for AI systems themselves. Yet the community lacks a common protocol for measuring how well frontier LLMs perform at this task. We introduce HarnessOpt-Bench, a benchmark for end-to-end harness optimization under expensive and stochastic evaluation. An optimizer, an LLM paired with a coding harness, receives a target agent's seed harness, graded evaluation feedback, and a fixed target-evaluation budget. It edits the harness and nominates a final candidate, which is scored by its normalized gain over the seed on a held-out test partition that remains inaccessible throughout search. A trusted execution environment enforces the evaluation boundary, meters target-agent resource use, and preserves candidate versions for audit. We evaluate 5 frontier LLMs as optimizers both under a shared coding harness and under their native harnesses across 4 downstream tasks, over 111 scored runs. Experiment results show that optimizer models separate more than the coding harnesses they act through, native harnesses are not consistently superior, and gains vary substantially across tasks and seed regimes. These results establish harness optimization as a measurable and discriminative capability with large space for improvement.

Varun Ursekar, Apaar Shanker, Yash Maurya +4

Scale AI

Large Language Model-Guided Optimization LLM Agent Evaluation Agent Harness Optimization LLM Agent Workflow Optimization AI Agent Benchmarks

Aug 6, 2026cs.AI

FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows

Agents used over time encounter recurring professional work: each case requires different evidence and judgment, while the underlying workflow can be reused. Benchmarks built from independent tasks cannot reveal whether an agent turns earlier experience into better procedures for later cases. We introduce FinEvo-Bench, a longitudinal benchmark designed around this structure. It contains 120 open-ended tasks drawn from real cases across 20 business scenes in six financial domains. Each scene contains six substantively different cases that share a professional workflow and an expert-authored rubric for task quality and financial compliance. Constructing and validating the benchmark required approximately 1,200 person-hours. Finance provides a natural test bed because recurring analyses apply shared professional and compliance requirements to heterogeneous inputs, producing case-specific analyses and conclusions. We evaluate four self-evolving agent scaffolds with Qwen3.7-Max on three independently shuffled, globally interleaved task streams. A Claude Code rubric judge backed by Claude Opus4.6 evaluates all outputs, and paired state-reset controls estimate each scaffold's gain from retained experience. Evolving runs score 9.33--19.37 points higher and trigger 0.12--0.44 fewer compliance issues per task than their paired controls. Paired score gains at within-scene ranks4--6 exceed those at ranks~1--3 by 6.10--8.70 points. FinEvo-Bench measures whether retained experience improves later professional work under continued use.

Bo Deng, Kang Zhou, Lifan Guo +6

Beihang University · Qwen DianJin Team, Alibaba Cloud Computing

Long-Horizon Agent Evaluation AI Agent Benchmarks Finance Self-Evolving Agents

Aug 6, 2026cs.AI

Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents

Investment competence is inherently personalized: the same market evidence can justify different actions for investors with different goals, horizons, portfolios, and risk boundaries. Yet financial LLMs are evaluated either by static question answering or by terminal profit and loss. The former omits agency; the latter cannot reveal whether a profitable action was grounded, profile-consistent, or merely lucky. We ask whether the community is using the wrong ruler for consequential agents. We introduce \textsc{InvestLogicBench}, a process-native benchmark containing 201,247 documented decisions from 151 real-world investors. Each episode instantiates a \textbf{P

\rightarrow

E

\rightarrow

R

\rightarrow

D

\rightarrow

O} trace: investor \textit{Profile}, observable market \textit{Events}, investment \textit{Reasoning}, executable \textit{Decision}, and delayed \textit{Outcome}. The release includes profile construction, point-in-time event binding, structured logic, horizons, outcomes, and post-mortems, and supports comprehension, profile-conditioned generation, and end-to-end replay. Across four leading LLMs, logical plausibility remains near 4/5 while event grounding is only 0.8--2.8/5; return and process quality also disagree. These results expose polished but weakly grounded reasoning that outcome-only evaluation hides. We further argue that P

\rightarrow

E

\rightarrow

R

\rightarrow

D

\rightarrow

O should be a data-system interface, requiring versioned profiles, temporal provenance, inspectable retrieval, decision ledgers, and replayable outcomes. Finance is our stress test for a broader class of personalized, consequential agents.

Yuanhong Jiang, Jingjie Zou, Zhenghong Lin +4

AI-Assisted Decision Making LLM Agent Evaluation AI Agent Benchmarks LLM Decision-Making Finance Financial Decision-Making

Aug 6, 2026cs.LG

Predicting Task Difficulty Without Rollouts

A fundamental challenge in evaluating and training autonomous agents is measuring the intrinsic difficulty of the tasks they attempt. Estimating this quantity can be useful for environment designers creating synthetic data or benchmarks, as well as for constructing training curricula, thereby offering a way to reduce compute costs. Such an estimation becomes increasingly important as agents (particularly LLM-based) move into longer-horizon domains, where empirical trial-and-error becomes a severe computational bottleneck. However existing work is largely confined to static tasks and relies on evaluation metrics that, as we show, can give an incomplete picture of predictive performance. In this paper we study ex ante difficulty prediction across 17 agentic benchmarks spanning coding, mathematics, machine learning, web navigation, function calling, and other domains. We find that AUC can mask poor difficulty estimates, identify token-level entropy as a useful predictive signal, and demonstrate how residuals between expected and observed difficulty can expose environment flaws such as contamination and infeasibility.

Stefan Krsteski, Charlotte Meyer

Andromede AI

Long-Horizon Agent Evaluation AI Agent Benchmarks

Aug 6, 2026cs.AI

Unified Agent: Managing Interactions across Devices

As capabilities rapidly increase, AI agents can move from running inside one app to acting across a user's devices over time. Yet existing agent systems still fall short in this scenario. This is because observations are scattered across devices and moments, but mainstream systems are not designed around this fact: a single agent that treats devices as tools lacks effective state management for all devices across time, and multi-agent systems coordinate across agents but do not maintain the compact carried state a cross-device, cross-time request needs. We argue that the agent should maintain an effectively designed state that organizes engagement evidence, stated facts, and the standing request in a compact, action-ready form for deciding its action given the current observation. To compare state designs, we construct a benchmark of user-agent interaction across devices and time. We instantiate this principle in Unified Agent, a stateful agent that carries interaction evidence across devices and moments and uses it with the current observation to act. In the default setting, it significantly outperforms our adaptations of four published designs. Across changes in multimodal large language model (MLLM) family, capability, and reasoning effort, it remains ahead of all compared systems, demonstrating that the state-design advantage is robust across MLLM settings. Our code and data will be publicly available on GitHub.

Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei +2

University of California, San Diego San Diego, CA, USA

AI Agent Benchmarks State Tracking Long-Horizon LLM Agents Memory-Augmented Agents

Aug 6, 2026cs.CV

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding

Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio-visual streams and maintain hour-scale memory. However, current evaluations predominantly rely on brief clips and multiple-choice formats. This design allows minimal baselines that process only the last four frames to match or surpass complex streaming models, while answer options also expose language shortcuts. We introduce StreamArena, a benchmark for hour-scale, interactive streaming video understanding. StreamArena contains 243 full-length videos averaging 88.8 minutes and 3,646 rigorously annotated, open-ended question-answer pairs that evaluate real-time perception, historical retrospection, proactive interaction, and multimodal tool utilization. Evaluation across diverse systems exposes a tension between continuous interaction and long-horizon multimodal comprehension. Methods that retain only recent frames cannot recover distant events, methods that convert past observations into text lose visual evidence, and methods that repeatedly compress visual memory struggle to preserve fine-grained details over time. We address this tension with StreamMind, a two-tier architecture that assigns latency-critical interaction and proactive monitoring to independently scheduled frontend workers, while backend workers asynchronously construct persistent multimodal memory and perform historical recall and external search. StreamMind outperforms existing streaming baselines across all four capabilities and reduces query-to-answer latency by reusing persistent state.

Xichen Zhang, Guankai Li, Yinghao Zhu +6

The Hong Kong University of Science and Technology · Xiaohongshu Inc. · The University of Hong Kong +1

Memory-Augmented VLMs Streaming Video Understanding AI Agent Benchmarks Long-Video Understanding Multimodal Agents

Aug 6, 2026cs.AI

SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution

LLM agents increasingly execute long-horizon tasks through tool use and environment interaction, shifting evaluation from final-response scoring to verification of complete executions. For skill-augmented agents, verification additionally requires the procedural knowledge encoded in task-time skills, because this knowledge indicates what evidence to inspect and which failures are task-critical. However, existing judge benchmarks often expose final responses or static trajectories, and rarely combine task-time skills with directly inspectable artifacts and environments. We therefore introduce SkillTV-Bench, a 681-case benchmark of real agent trajectories from 50 tasks across eleven domains, designed to evaluate skill-aware trajectory verification for both LLM-as-a-Judge and Agent-as-a-Judge methods. Additionally, we propose SkillTV-Evolve, which externalizes verification knowledge as a reusable JudgeSkill that guides an agent judge to plan targeted inspections and issue evidence-grounded verdicts. On a disjoint development pool, an automated evolution loop further refines the JudgeSkill using misjudged cases. On SkillTV-Bench, the refined skill increases the same agent judge's accuracy by 14.8 percentage points. In offline rollout-pool selection, it increases selected-trajectory success from 22.9% with one rollout to 45.5% with ten rollouts. The code and data are available at https://github.com/HanZhi306/SkillTV-Bench

Zhi Han, Chenxi Zeng, Liuhaichen Yang +3

Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · University College London +1

LLM-as-a-Judge Long-Horizon Agent Evaluation AI Agent Benchmarks

Aug 6, 2026cs.AI

EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents

Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic. In deployment, however, the choice among a local lookup, broad search, composite research tool, stronger model, or human escalation is part of the task itself. We introduce EcoAgent-Bench, in which every task specifies priced actions and an explicit budget. Its 304 real-derived tasks span five families adapted from GAIA, HotpotQA, and MuSiQue, and test four decisions: avoiding unnecessary escalation, escalating when local evidence is insufficient, selecting a model tier, and stopping on unsupported premises. We evaluate seven LLM agents in tool-API and workspace-CLI settings, together with four oracle scripted controls. Micro-averaged accuracy rewards one-sided policies: always-escalate controls achieve high micro success while failing save-oriented tasks. We therefore also report an economic-consistency score (the worse of accuracy on upgrade-oriented and save-oriented family groups) which exposes this failure. Tool-API agents attain only 3.9-24.0% micro strict success (at most 7.3% economic consistency), often either stopping before warranted escalation or overspending on cheap tasks. A threshold-crossing budget sweep changes GPT-5.4's escalation rate from 0% to only 3%. These results show that completion under a budget and economical action selection are distinct properties. We release the task bundle, transformation pipeline, frozen evaluation environments, and integrity-bound result artifacts needed to study both.

Jie Wu, Ming Gong, Feixiang Cheng +1

Atlassian

Computer-Use Agent Benchmarks Tool-Use Evaluation LLM Agent Evaluation AI Agent Benchmarks LLM Decision-Making

Aug 5, 2026stat.ML

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough

Multi-agent LLM systems route among model-backed advisors, yet a deployer rarely knows before shipping whether routing will help at all. Prevailing routers optimize a gate's AUC and presume that advisor complementarity suffices. We show that neither determines the deployable gain. We introduce RouteGuard, a deployment-certification framework. Routing gain decomposes as

G = πΔ_E

, and the achievable gain is governed by a conditional-regret functional

Φ

, not by AUC. A finite-sample certification bracket comes with a matching Le Cam lower bound, constant-sharp over the fixed-activity class, and a robustness phase transition. On two benchmarks the framework acts as a guardrail. On RouterBench (11 cross-family models) the verdict depends on the sampling unit: the protocol certifies a gain over GPT-4 under prompt-level sampling and withholds it under workload-cluster resampling, because the gain rests on 3 of 86 workload cells. On OpenRCA (three Gemini advisors) the advisors are statistically redundant: the realized oracle sits at or below the independence baseline in all pools we tested (221 RouterBench pools and three OpenRCA distributions), so the protocol correctly refuses to certify. A pre-registered semi-synthetic control confirms calibration: the protocol certifies a genuine gain once

m \ge m^\star

and does not certify a true null. Code and frozen artifacts will be released with the published version.

Anchen Sun, Kaiqi Yang

Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL 33146 USA · Department of Mathematics, University of Miami, Coral Gables, FL 33146 USA

Multi-Agent LLM Systems AI Agent Benchmarks LLM Routing LLM Agent Routing

Aug 4, 2026cs.MA

Strategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical Systems

LLM-agent evaluations commonly measure task success or agreement with a declared plan. In strategic cyber-physical systems, an architecture must also remain appropriate after autonomous participants respond and physics constrains outcomes. We introduce a controlled benchmark of planning-induced control trajectories: ordered planning operations and directives linking execution architecture to strategic response and physical consequences. Four coded executors (predefined, sequential, hierarchical, and search) control demand response for 40 prosumers on a radial feeder. The LLM declares or advises typed policies and mediates communication; schedules, base prosumer dynamics, stochastic actions, and power flow remain explicit code. Paired forced-mode counterfactuals, exact-prompt caching, common response draws with separate randomness streams, critic isolation, and event-level feasibility isolate comparisons. The Llama-3.3-70B experiments on this feeder distinguish three properties. First, forced search is the oracle in all five baseline seeds under the specified objective. Second, injected objective substitution preserves mode agreement at 1.0 while increasing cumulative voltage shortfall by 2.68x. Third, the 144-scenario, 576-episode factorial bank, using three repeated seeds, contains feasible oracles from predefined, sequential, and search. The prespecified stress-held-out ridge has mean regret 90.7 and no observed value over fixed sequential. A post-hoc constraint-aware analysis reduces regret to 29.0; a simple deadline rule attains 28.7, so this gain does not establish a learning advantage. An all-feasible ablation does not improve over fixed search. These are simulation-internal, descriptive comparisons. A five-model, 300-declaration extension tests interface behaviour, not cross-backbone physical rankings; shared-endpoint latency tails motivate probabilistic live feasibility.

J. de Curtò, I. de Zarzà

Department of Computer Applications in Science and Engineering, BARCELONA Supercomputing Center, Barcelona, Spain · Escuela T´ecnica Superior de Ingenier´ıa (ICAI), Universidad Pontificia Comillas, Madrid, Spain · Human-Centered AI, Data and Software, LUXEMBOURG Institute of Science and Technology, Esch-sur-Alzette, Luxembourg

Cyber-Physical Systems LLM Planning LLM Agent Evaluation AI Agent Benchmarks Demand Response

Aug 4, 2026cs.AI

FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables

Evaluating financial AI agents requires criteria aligned with real professional work. Existing rubric methods typically derive criteria from task prompts or model outputs, overlooking tacit standards visible only in practitioner deliverables. We introduce FinProBench, a benchmark for professional financial tasks, and Role-Grounded Rubric Construction (RGRC), a reusable pipeline that derives rubrics from deliverables produced by practitioners in the same role. RGRC comprises four stages: Deliverable Collection, Competency Extraction, Rubric Synthesis, and Validation. Its rubrics capture tacit standards, distinguish quality levels, and transfer across tasks within a role. Before analysis, we classified 57 occupations by deliverable genre into 30 prior-rich conventional roles and 27 prior-sparse role-specialized roles. Across all roles, Prompt-only nearly matches RGRC for conventional roles (89.2% vs. 90.7%), but RGRC substantially outperforms it for role-specialized roles (99.1% vs. 78.0%). This split indicates that prompt engineering can approximate rubrics when conventions are well represented in model priors, while professional grounding is essential for standards beyond those priors. FinProBench is built from 1,723 curated deliverables spanning 57 occupations, 8 financial sub-industries, and 161 deliverable types, and releases an initial evaluation set of 20 complete tasks covering 20 roles in 7 sub-industries. With heterogeneous LLM judges and role-level rubrics, human deliverables rank first on average (73.7 vs. 70.3, 70.2, and 69.6 out of 100), while all four systems show overlapping 95% confidence intervals and complementary strengths. Reusing rubrics at the role level reduces estimated per-task construction effort by 6.7 times relative to authoring each rubric from scratch.

Ben Wang, Kang Zhou, Lifan Guo +2

Qwen DianJin Team, Alibaba Cloud Computing

AI Agent Evaluation AI Agent Benchmarks Rubric-Based Evaluation Finance

Aug 4, 2026cs.CV

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration. Preliminary evaluations reveal two critical bottlenecks in current models: (1) modality bias, where agents bypass visual tools in favor of textual search, and (2) parametric knowledge leakage, where models rely on internal memory rather than genuine tool-augmented execution. To address these challenges, we propose Video-DR, featuring a decoupled perception-exploration pipeline with stage-wise tool unlocking that compels exhaustive cross-frame visual grounding prior to web retrieval. Our framework adopts a two-stage training recipe: supervised fine-tuning followed by Group Relative Policy Optimization (GRPO), enabling autonomous exploration that breaks the imitation-learning ceiling. Furthermore, we curate Video-DR-Bench, a human-AI collaborative benchmark comprising 200 complex, multi-hop VQA instances. Empirical results demonstrate that our Video-DeepResearch-35B-A3B establishes a new state-of-the-art of 64.0% average accuracy, surpassing proprietary Claude-4.5-Sonnet (59.0%) by 5.0 points and significantly outperforming GPT-5 (52.5%) and Gemini 2.5 Pro (57.5%). The 30B-A3B variant achieves 59.3%, competitive with Claude-4.5-Sonnet and demonstrating the effectiveness of our training paradigm even at compact scale. Code: https://github.com/Osilly/Vision-DeepResearch.

Zhen Fang, Yu Zeng, Wenxuan Huang +17

Deep Research Agents Video QA AI Agent Benchmarks Tool-Using Vision-Language Agents Autonomous Research Agents

Aug 4, 2026cs.AI

ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?

Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these systems can effectively evolve their skills and whether the resulting skills improve task-solving capabilities. To bridge this gap, we introduce ContinualSkillBench, a dynamic evaluation framework for in-context continual skill learning. It covers five representative domains, each containing 100 interconnected subtasks ordered by increasing difficulty and opportunities for cross-task skill reuse. Our experiments show that sequential execution generally improves performance, but the gains vary substantially across models and domains. Moreover, in-context learning performs comparably to explicit skill maintenance on average, suggesting that much of the improvement arises from adaptation to prior context and feedback rather than reusable skill abstraction alone. Explicit skills nevertheless provide selective benefits for tasks requiring reusable procedures or precise outputs. We further find that less capable models tend to accumulate larger, more fragmented collections of task-specific skills. These findings show that current in-context skill evolution mechanisms can support continual adaptation, but still struggle to consistently consolidate experience into robust and transferable skills.

Tianyi Guan, Yiding Wang, Haotong Yang +5

Institute for Artificial Intelligence, Peking University · 2Beijing Institute for General Artificial Intelligence

Continual Learning for LLM Agents LLM Agent Evaluation LLM Agent Skill Learning AI Agent Benchmarks

Aug 4, 2026cs.AI

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks

Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively. Evaluating self-evolution is difficult: existing benchmarks provide limited coverage of economically valuable task domains, do not always design training and test tasks such that test-time gains can be attributed to training experience, and remain vulnerable to data contamination. We present GDPevo, an evolution-native benchmark grounded in GDP-related enterprise workflows, together with the fully automated data pipeline that generates it. Its core mechanism, rule hybridization, decomposes each enterprise workflow into atomic business rules, distributes subsets of these rules across training tasks, and recombines them in held-out test tasks so that test-time gains are attributable. GDPevo spans CRM, ERP, finance, healthcare, legal, and data-centric workflows. Its V1 release contains 120 tasks in 12 groups, with five training and five held-out test tasks per group. Full automation enables the pipeline to expand the suite to 240 tasks in 24 groups (V2) within two days, providing a practical response to contamination. Using GDPevo, we evaluate four agents, each comprising a harness and a model, under four supervision types. Self-evolution consistently improves held-out accuracy by up to 16.44 percentage points. But the best evolved agents remain far below the fully informed oracle ceiling of 91.6%, indicating that the self-evolution ability of current agents remains far from fully realized. We publicly release the pipeline, benchmark, and full evaluation results at https://github.com/Prism-Shadow/GDPevo.

Leijun Zhou, Zhihao Liu, Xiang Qu +9

PrismShadow · New York University

LLM Agent Evaluation AI Agent Benchmarks Self-Evolving Agents

Aug 4, 2026cs.AI

Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities

Benchmarking the ability of AI scientists to generate novel ideas is notoriously difficult. Existing benchmarks in this field have made progress in evaluating scientific reasoning and research replication, but often rely on synthetic tasks or retrospective targets, which may be confounded by prior exposure. We hypothesize that complex, adversarial, fast-moving real-world domains where expert practitioners independently generate observable outputs can provide a practical solution to fill this gap and evaluate the capabilities needed for AI scientists, including reasoning, novelty, and hypothesis formulation. We instantiate this framework in two structurally different domains, Formula 1 (F1), where models ideate around car design concepts for the 2026 season, and real pre-season innovations provide a ground truth, and Magic: The Gathering (MTG), where models propose decks from a recently updated card pool and are evaluated against 19 Pro Tour (PT) decklists. Across both domains, models produce plausible outputs, but few align with real-world expert solutions. In F1, the best model, GPT-5.2 matched 10 of 40 real innovations with 166 ideas proposed across runs. In MTG, the best deck from Gemini 3 Flash recovered 5 of 7 new-set cards from the third-place PT deck, and across all 108 decks, the cards models selected most often were also the cards most widely adopted by PT decks (Spearman

ρ= 0.74

,

p = 0.0003

). These results suggest that a key capability gap for AI scientists is not idea generation, but filtering, prioritization, and coherent novelty.

William Bolton, Philip Torr

Department of Engineering Science, University of Oxford, Oxford, United Kingdom.

AI Agents for Scientific Discovery Benchmark Design Scientific Hypothesis Generation AI Agent Benchmarks Research Idea Generation

Aug 4, 2026cs.AI

Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Autonomous Experimental Design

AI for Research (AI4Research) leverages AI to automate and improve scientific workflows. While experimental design is a critical stage of the research process, prior work has focused primarily on code implementation and execution, overlooking the importance of this stage, and no benchmark exists to evaluate AI's ability to conduct systematic experiment design. To bridge this gap, we propose SCOPE, a Scientific COmprehensive Planning Evaluation Benchmark constructed from 300 high-quality latest papers across 19 research domains from top-tier venues (e.g., ICML, NeurIPS, and ICLR),evaluating LLMs on two dimensions: High-Level planning completeness (main, ablation, and analysis experiments) and Low-Level configuration accuracy and rationality (datasets, baselines, and metrics). Benchmarking reveals three findings: (1) most LLMs cannot directly design high-quality experiments; (2) all LLMs exhibit a performance bottleneck in low-level configuration; and (3) search mode does not improve design quality. Furthermore, to address these challenges, we propose OptED, a novel agentic workflow to optimize LLM-based experimental design, that enhances LLM-based experimental planning through stage isolation, tool augmentation, and rule-based constraints, effectively alleviating the configuration bottleneck.

Zejun Liu, Jian Wu, Ru Peng +4

Westlake University · Zhejiang University · Nanjing University of Science and Technology +1

AI for Science Benchmark Design AI Agent Benchmarks Large Language Model-Guided Scientific Discovery Autonomous Experimentation

Aug 4, 2026cs.CV

MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification

Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks predominantly focus on single-turn full-page generation from scratch, overlooking the iterative workflow of real-world frontend engineering, where developers repeatedly reconstruct missing regions and modify localized elements within existing codebases. To bridge this gap, we introduce MT-Web2Code, the first multimodal coding benchmark for multi-turn Macro-Level Regional Reconstruction and Micro-Level Localized Modification, which contains 102 tasks spanning 16 vertical domains. To construct deterministic repair trajectories without costly turn-level human annotation, we develop a scalable Reverse-Corruption Trajectory Engine that iteratively injects structural and stylistic defects into golden pages. We further propose a dual-axis evaluation protocol that measures target-region fidelity and the preservation of unaffected content, where regional reconstruction is assessed by a 5-dimensional VLM-based rubric and localized modification by deterministic pixel-grounded alignment. Experiments on 13 frontier coding agents reveal that current agents struggle to faithfully reconstruct target regions while preserving unaffected content, lack fine-grained visual-code alignment for localized edits, and suffer from error snowballing over multiple turns. Beyond benchmarking, our deterministic evaluation metrics provide fine-grained feedback signals that may facilitate future research on training iterative UI coding agents. Our evaluation code and data will soon be released.

Qiming Li, Shujie Hu, Haohan Liu +3

1Harbin Institute of Technology · 2Meituan, Longcat Team · 3Peng Cheng Laboratory

Code Generation AI Agent Benchmarks Code Generation Benchmarks

Aug 4, 2026cs.CY

EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners

Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS). Yet tutoring is long-horizon, since a learner improves over days and weeks rather than in a single turn, and no benchmark evaluates an agent tutor across a sustained relationship. We introduce EduClaw-Bench, a benchmark that places an agent tutor in a continuous 30-day relationship with a simulated learner grounded in knowledge tracing (KT), whose knowledge-concept mastery, from a KT model trained on real-student data, drives its answers and is probed for learning gain across 55 scenarios. Each agent is scored on three primary axes (learning gain, responsiveness, and helpfulness) and two curriculum-design axes (Gagné and Rosenshine), with helpfulness and the curriculum axes judged by a cross-family panel of three LLM judges. Evaluating 10 agent adapters over three base-model tiers yields two findings that single-tier, single-session evaluation cannot reach. First, tutoring quality belongs to the base model and the agent harness together rather than either alone. Second, almost no combination sustains good tutoring over the full horizon. A calibration check (

\text{ECE}=0.049

) and a live-classroom field study confirm that the simulated learner and its measurements track reality. Our work is a step toward trustworthy AI tutors for future education.

Unggi Lee, Sookbun Lee, Yeil Jeong +3

Korea University Sejong Campus · Opentutorials · Indiana University +2

Intelligent Tutoring Systems AI in Education LLM Agent Evaluation Long-Horizon Agent Evaluation AI Agent Benchmarks

Aug 4, 2026cs.AI

Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls

Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool and orchestrating the order of calls. However, correctly filling the parameters of a tool call is equally critical for successful execution and has received far less attention. In domains such as cloud networking, even frontier models correctly complete fewer than half of tool calls. Inspired by recent analyses showing that LLM hidden states encode rich information about model predictions, we discover that while the model generates a parameter value, its hidden state contains a strong correctness signal: a simple linear probe can accurately predict whether the value will be correct. Based on this observation, we propose a unified probe-guided framework with two complementary approaches: probe-filtered bootstrapped training (PBT), which uses the probe to filter reliable self-generated calls for fine-tuning, and probe-guided reranking (PGR), which uses the probe to select better candidates during inference. To support systematic evaluation, we release ParamBench, a benchmark built from real cloud-network APIs that categorizes every instance into five difficulty levels according to parameter nesting depth, cross-parameter dependencies, and the reasoning required to derive values from earlier calls. Extensive experiments across 5 open models on ParamBench and 6 external benchmarks demonstrate that our method substantially improves parameter generation, raising the average exact match from 19.7% to 59.6%.

Guoyao Yu, Xiaoqing Sun, Ziqi Huang +13

Tool-Augmented Language Model Agents AI Agent Benchmarks LLM Tool Use LLM Agent Training Tool Use

Aug 4, 2026cs.AI

UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks

Modern cities rely on an increasing number of digital services to operate, but residents' daily needs are still difficult to meet. Services are fragmented and have little interoperability, placing a heavy operational burden on users. Existing digital platforms, urban foundation models, and intelligent assistants each address only isolated aspects of an urban task. But they struggle to reliably convert complex natural-language requests into executable cross-system workflows. We propose Urban-Agent, a tool-augmented agent framework for cross-system urban tasks. It couples the cognitive and reasoning capabilities of a large language model with a tool-set supporting code execution, API calls, and Model Context Protocol. Through one adaptive closed loop, it clarifies missing information before acting, grounds tool use in live observations, and aligns the final response with observed evidence and task constraints. To address the evaluation gap, we introduce Urban-Eval, a benchmark specifically designed for cross-system urban request. Unlike prior benchmarks that assess either general tool use or urban knowledge and reasoning, Urban-Eval evaluates both task results and execution quality, including required tool coverage, dependency validity, and evidence traceability. Experimental results indicate that Urban-Agent reaches a 71% task success rate, 10 points above the strongest baseline. This lead holds across GPT-5-mini, Gemini-2.5-flash, DeepSeek-V4-flash, and Qwen3-235B-A22B.

Jiayu Cao, Xingyuan Zeng, feiyu Li +6

LLM Agent Evaluation AI Agent Benchmarks Tool-Using Language Agents

Aug 3, 2026cs.AI

ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision

LLM-agent evaluations often produce task outcomes long before the full benchmark run is complete. A partial score is tempting to report, but it does not show whether the observed tasks support the same conclusion as the completed evaluation. Early tasks can omit important parts of a benchmark, running cheaper tasks first can distort the observed sample, and a rule that decides only easy pairs can appear accurate while leaving many comparisons unresolved. We introduce ParEvalLayer, a decision layer that reads paired outcomes for two agent systems and a comparison policy chosen in advance. For each partial run, it records whether the tested agent system is better by the required amount, is not better by that amount, needs more evidence, or should abstain. We evaluate ParEvalLayer by replaying completed public benchmark data as if each evaluation had stopped earlier. At each point, ParEvalLayer applies the policy using only the outcomes observed so far; if it reaches one of the two comparison judgments, we check whether that judgment matches the completed data for the same system pair. With the main comparison rule, three of the public benchmarks reach the same decision as the completed evaluation after observing only 15% to 25% of task outcomes. Other benchmarks require more task outcomes. This variation shows why a partial score alone is not enough: reports should also state the decision rule and how many comparisons remain without a decision.

Wei-Jung Huang, Bonan Shen

Independent Researcher · United States

Pairwise Comparison LLM Agent Evaluation AI Agent Benchmarks Automated Evaluation

Aug 3, 2026cs.AI

Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce

In vibe coding, people describe software in natural language and delegate implementation to AI agents. By analogy, vibe commerce allows people to express buying or selling goals in natural language and delegate the corresponding tasks to agents. Commerce, however, requires independently controlled Buyer and Merchant agents to interact in a shared market while preserving their private objectives and distinct authority. We introduce Agentic Commerce World (ACWorld), an environment for evaluating such agents across ongoing transactions. Through its Vibe Commerce Protocol (VCP), ACWorld validates agent actions before updating shared transaction state and records the resulting interactions, making agent behavior auditable and evaluation reproducible. The ACWorld Benchmark contains a 200-task capability-coverage track and a 60-task large-catalog track that searches 785,022 transactable listings. Across ten models, mean scores range from 65.9% to 85.6% and from 56.1% to 91.4%, respectively. Our analysis shows that process-level evidence is necessary: final state alone can miss evaluated errors, incomplete trajectories still retain useful process signals, and large-catalog tasks expose bottlenecks across stages.

Shicheng Fan, Mingdai Yang, Duohao Wang +9

University of Illinois at Chicago · 2Springbrand · 3Northwestern University +6

AI Agent Evaluation Agent Evaluation AI Agent Benchmarks Agentic Commerce Agentic AI

Aug 3, 2026cs.CL

PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise

Large Language Models (LLMs) are increasingly deployed in task-oriented dialogue systems that support multi-step decision-making in high-stakes domains such as education, healthcare, and finance. However, existing benchmarks typically assume perfectly accurate tool outputs, overlooking the reality that deployed systems must operate with noisy tools and human decision-makers whose trust in the agent is itself uncertain. Such conditions are common in practice, for example, a clinician using a diagnostic prediction tool or an advisor relying on a model that forecasts student outcomes from historical records. We introduce PREDACTBENCH, a benchmark for evaluating dialogue agents paired with statistically imperfect tools, using education as a measurable testbed where ground truth outcomes and clear intervention decisions are available. First, we build a benchmark for AI-assisted human decision-making, where the AI uses noisy predictors to help guide a user. Second, we introduce episode-level Relative AI-Reliance (RAIR) and Relative self-reliance (RSR) metrics, extending prior trust calibration framework to multi-turn dialogue. Third, we evaluate 13 state-of-the-art closed and open source LLMs on two educational datasets, OULAD (real assessment trajectories from the UK Open University) and PREDACT-CS (60 courses with real final grade outcomes and synthetically generated weekly score trajectories), alongside a human study with instructors and teaching assistants. We find that when tools are noisy, SOTA models are supposed to provide visibility to teachers so that they do not over-rely on wrong suggestions or hallucinations, but current models fail to do that. We offer PREDACTBENCH to help build better LLMs as AI decision support systems to help teachers.

Abdulrahman AlRabah, Xiaocheng Yang, Dilek Hakkani-Tür +1

University of Illinois Urbana-Champaign

AI Agent Reliability AI-Assisted Decision Making Tool-Augmented Language Model Agents AI in Education AI Agent Benchmarks LLM Tool Use+1

Aug 3, 2026cs.CL

ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step

To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone, even in the absence of documentation. However, existing tool-use benchmarks expose semantic tool schemas in static environments, allowing agents to rely on prior knowledge rather than autonomous discovery. To address this limitation, we introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning. By removing semantic cues and enforcing a continuous task curriculum, the benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction. The benchmark further introduces dynamic challenges, including mapping drift, stochastic action failures, and temporal execution windows, to evaluate whether agents can revise and adapt their hypotheses as the environment changes. Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation. When faced with structural changes such as mapping drift, agents fail to use deductive strategies such as cycle tracing, and instead exhibit belief inertia or fall back to exhaustive search. Increasing test-time reasoning only amplifies this expensive brute-force search rather than enabling deductive recovery. While equipping agents with persistent memory reduces compounding errors, they remain unable to efficiently infer structural changes, highlighting a gap in current agent reasoning.

Vernon Toh, Navonil Majumder, Zhengyuan Liu +2

DeCLaRe Lab, Nanyang Technological University, Singapore · Agency for Science, Technology, and Research (A*STAR), Singapore

LLM Agent Evaluation AI Agent Benchmarks Tool-Using Agents Tool Use

Aug 3, 2026cs.AI

From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents

Large Language Models have enabled increasingly capable autonomous agents, yet personalization remains critical for making such agents practically useful. Recent benchmarks have begun evaluating personalization in agents, but they largely rely on static preference snapshots, fixed interaction logs, or question answering over predefined user profiles. Such designs fail to capture the complexity of evolving user preferences and neglect preference-conditioned task execution-a discrepancy we term as the knowledge-to-action gap. To address this challenge, we introduce IBA-Bench, a benchmark for implicit behavioral alignment constructed from longitudinal interaction histories that contain noise, implicit cues, and temporal inconsistencies. Unlike prior work, IBA-Bench evaluates whether an agent can execute tasks while satisfying implicit user constraints inferred from historical interactions. We further propose IBA-Agent, an agent framework that reconciles conflicting priorities through broad retrieval and trajectory-level alignment. Experiment results on IBA-Bench show that effective personalization remains a significant challenge for state-of-the-art LLM agents, and the proposed IBA-Agent substantially improves behavioral alignment in complex scenarios across nine application domains.

Jiajia Song, Bobo Li, Haiwen Yi +6

National University of Singapore · University of Toronto · University of Minnesota Twin Cities +2

LLM Personalization LLM Agent Evaluation AI Agent Benchmarks

Aug 3, 2026cs.CL

CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship

LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and prompted simulators, aggregate empathy into one score, and overlook judge biases such as same-family favoritism and scale drift. We introduce CompanionBench, an interactive bilingual benchmark. To our knowledge, it is the first companion benchmark to ground both its scenarios and a trained user simulator in de-identified real-world data. A hidden disclosure gate branches each persona's trajectory on the agent's own behavior, controlling the interaction state space without scripting dialogue. We operationalize ten capabilities derived from 25 theories across psychology and counseling, four of them not graded explicitly by prior work: holding ambiguity, selfobject responsiveness, positive resonance and calibrated challenge. Agents are assessed on two complementary axes: a subjective ten-capability rubric and a deterministic measure of whether deeper disclosure was earned. A cross-family panel dilutes same-family favoritism; an Item Response Theory model separates agent quality from judge severity. Theory fixes what to measure and how personas are structured; real data supply events, history, and profiles -- coverage from theory, authenticity from data. Rankings are reproducible in both languages (rho = 0.996 ZH / 0.953 EN). Evaluating 28 agents reveals capability-level differences obscured by aggregate scores. Emotion regulation and calibrated challenge remain common weaknesses; holding ambiguity discriminates most. Role-play agents rank near the bottom: immersion does not imply relational competence. Across agents, the dominant failure mode is substituting surface warmth for substantive relational support. We will release 500 Chinese-English parallel pairs and the evaluation code.

Yao Liu, Guangjia Chai, Yuming Huang +3

Emotional Support Conversation AI Companions AI Agent Benchmarks Multi-Turn Dialogue Evaluation

Aug 3, 2026cs.SE

BulkPR-Bench: Benchmarking Queue-Level Governance of Interacting Pull Requests

Coding-agent benchmarks increasingly cover long-horizon, end-to-end, and interactive development, but typically retain one requested outcome or a fixed change sequence. Sequential policies can process a pull-request (PR) queue one candidate at a time, but when queued PRs interact, maximizing safe delivery can require jointly deciding which changes to merge and in what order. We introduce BulkPR-Bench, an executable benchmark in which an agent must recover consequential PR relations and return a large safe subset in executable order under a rolling-release protocol. The suite contains 581 newly authored candidate PRs on frozen snapshots of 18 real repositories. Registered state-by-state repository execution, including hidden safety checks, validates the gold relation graph; an exact oracle then computes the largest safe subset. Our primary metric, Relational Delivery Score (RDS), scores safe delivery and correct rejection over relation groups from the realized merge trace; Global Safety-Gated Yield (Global-SGY) separately measures strict delivery of the realized whole-queue plan. Under the buffered primary protocol with batch size

K=32

, the three highest RDS estimates among the six models are 66.6%, 62.0%, and 57.9%, compared with 53.1% for the strongest sequential baseline. Only 8 of 324 model runs complete a queue exactly. Critical-relation recall ranges from 35.2% to 57.7%, and diagnostic runs supplied with the gold relations show substantial remaining headroom. Gains on relation groups therefore do not yet translate into dependable whole-queue governance.

Zetong Xiong, Qiao Zhao, Jun Zhang +20

Baidu Beijing, China

Software Engineering Agents Benchmark Construction Software Engineering Benchmarks AI Agent Benchmarks